智慧农业（中英文）2024，Vol.6Issue(2)：118-127,10.DOI:10.12133/j.smartag.SA202401005
基于改进YOLOv8s的玫瑰鲜切花分级方法
Grading Method of Fresh Cut Rose Flowers Based on Improved YOLOv8s
摘要
Abstract
[Objective]The fresh cut rose industry has shown a positive growth trend in recent years,demonstrating sustained development.Con-sidering the current fresh cut roses grading process relies on simple manual grading,which results in low efficiency and accuracy,a new model named Flower-YOLOv8s was proposed for grading detection of fresh cut roses. [Methods]The flower head of a single rose against a uniform background was selected as the primary detection target.Subsequently,fresh cut roses were categorized into four distinct grades:A,B,C,and D.These grades were determined based on factors such as col-or,size,and freshness,ensuring a comprehensive and objective grading system.A novel dataset contenting 778 images was specifical-ly tailored for rose fresh-cut flower grading and detection was constructed.This dataset served as the foundation for our subsequent ex-periments and analysis.To further enhance the performance of the YOLOv8s model,two cutting-edge attention convolutional block at-tention module(CBAM)and spatial attention module(SAM)were introduced separately for comparison experiments.These modules were seamlessly integrated into the backbone network of the YOLOv8s model to enhance its ability to focus on salient features and suppressing irrelevant information.Moreover,selecting and optimizing the SAM module by reducing the number of convolution ker-nels,incorporating a depth-separable convolution module and reducing the number of input channels to improve the module's efficien-cy and contribute to reducing the overall computational complexity of the model.The convolution layer(Conv)in the C2f module was replaced by the depth separable convolution(DWConv),and then combined with Optimized-SAM was introduced into the C2f struc-ture,giving birth to the Flower-YOLOv8s model.Precision,recall and F1 score were used as evaluation indicators. [Results and Discussions]Ablation results showed that the Flower-YOLOv8s model proposed in this study,namely YOLOv8s+DW-Conv+Optimized-SAM,the recall rate was 95.4%,which was 3.8%higher and the average accuracy,0.2%higher than that of YO-LOv8s with DWConv alone.When compared to the baseline model YOLOv8s,the Flower-YOLOv8s model exhibited a remarkable 2.1%increase in accuracy,reaching a peak of 97.4%.Furthermore,mAP was augmented by 0.7%,demonstrating the model's superior performance across various evaluation metrics.The effectiveness of adding Optimized-SAM was proved.From the overall experimen-tal results,the number of parameters of Flower-YOLOv8s was reduced by 2.26 M compared with the baseline model YOLOv8s,and the reasoning time was also reduced from 15.6 to 5.7 ms.Therefore,the Flower-YOLOv8s model was superior to the baseline model in terms of accuracy rate,average accuracy,number of parameters,detection time and model size.The performances of Flower-YO-LOv8s network were compared with other target detection algorithms of Fast-RCNN,Faster-RCNN and first-stage target detection models of SSD,YOLOv3,YOLOv5s and YOLOv8s to verify the superiority under the same condition and the same data set.The aver-age precision values of the Flower-YOLOv8s model proposed in this study were 2.6%,19.4%,6.5%,1.7%,1.9%and 0.7%higher than those of Fast-RCNN,Faster-RCNN,SSD,YOLOv3,YOLOv5s and YOLOv8s,respectively.Compared with YOLOv8s with higher recall rate,Flower-YOLOv8s reduced model size,inference time and parameter number by 4.5 MB,9.9 ms and 2.26 M,respec-tively.Notably,the Flower-YOLOv8s model achieved these improvements while simultaneously reducing model parameters and com-putational complexity. [Conclusions]The Flower-YOLOv8s model not only demonstrated superior detection accuracy but also exhibited a reduction in model parameters and computational complexity.This lightweight yet powerful model is highly suitable for real-time applications,making it a promising candidate for flower grading and detection tasks in the agricultural and horticultural industries.关键词
YOLOv8s/玫瑰鲜切花/分级检测/深度学习/SAM/注意力机制Key words
YOLOv8s/fresh cut roses/hierarchical detection/deep learning/SAM/attention mechanism分类
信息技术与安全科学引用本文复制引用
张玉玉,邴树营,纪元浩,严蓓蓓,许金普..基于改进YOLOv8s的玫瑰鲜切花分级方法[J].智慧农业（中英文）,2024,6(2):118-127,10.基金项目
山东省自然科学基金面上项目(ZR2022MC152) （ZR2022MC152）
山东省重大科技创新工程项目(2021LZGC014-3) （2021LZGC014-3）
青岛市产业培育计划科技惠民专项(23-1-3-6-zyyd-nsh) Shandong Province Natural Science Foundation General Project(ZR2022MC152) （23-1-3-6-zyyd-nsh）
Shandong Province Major Sci-ence and Technology Innovation Project(2021LZGC014-3) （2021LZGC014-3）
Qingdao City Industrial Cultivation Plan Science and Technology Bene-fit People Special Project(23-1-3-6-zyyd-nsh) （23-1-3-6-zyyd-nsh）
